{
"openapi": "3.0.1",
"info": {
"title": "BeautifulSoup Scraper",
"description": "Crawls websites using raw HTTP requests. It parses the HTML with the BeautifulSoup library and extracts data from the pages using Python code. Supports both recursive crawling and lists of URLs. This Actor is a Python alternative to Cheerio Scraper.",
"version": "0.1",
"x-build-id": "nzoHH0HZdtYkaXURF"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/apify~beautifulsoup-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-apify-beautifulsoup-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/apify~beautifulsoup-scraper/runs": {
"post": {
"operationId": "runs-sync-apify-beautifulsoup-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/apify~beautifulsoup-scraper/run-sync": {
"post": {
"operationId": "run-sync-apify-beautifulsoup-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
}
},
"components": {
"schemas": {
"inputSchema": {
"type": "object",
"required": [
"startUrls",
"pageFunction",
"proxyConfiguration"
],
"properties": {
"startUrls": {
"title": "Start URLs",
"type": "array",
"description": "A static list of URLs to scrape.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"maxCrawlingDepth": {
"title": "Max crawling depth",
"minimum": 0,
"type": "integer",
"description": "Specifies how many links away from the Start URLs the scraper will descend. Note that pages added using context.request_queue in Page function are not subject to the maximum depth constraint.",
"default": 1
},
"requestTimeout": {
"title": "Request timeout",
"minimum": 1,
"type": "integer",
"description": "The maximum duration (in seconds) that processing a single page may take before it times out. This limits the request handler that runs your Page function.",
"default": 10
},
"linkSelector": {
"title": "Link selector",
"type": "string",
"description": "A CSS selector stating which links on the page (<a> elements with href attribute) shall be followed and added to the request queue. To filter the links added to the queue, use the Link patterns field.
If the Link selector is empty, the page links are ignored. Of course, you can work with the page links and the request queue in the Page function as well."
},
"linkPatterns": {
"title": "Link patterns",
"type": "array",
"description": "Link patterns (regular expressions) to match links in the page that you want to enqueue. Combine with Link selector to tell the scraper where to find links. Omitting the link patterns will cause the scraper to enqueue all links matched by the Link selector.",
"items": {
"type": "string"
}
},
"pageFunction": {
"title": "Page function",
"type": "string",
"description": "A Python function, that is executed for every page. Use it to scrape data from the page, perform actions or add new URLs to the request queue. The page function has its own naming scope and you can import any installed modules. Typically you would want to obtain the data from the context.soup object and return them. Identifier page_function can't be changed. For the fields available on the context object, see the BeautifulSoupCrawlingContext reference. Asynchronous functions are supported."
},
"soupFeatures": {
"title": "BeautifulSoup parser",
"enum": [
"html.parser",
"lxml",
"xml",
"html5lib"
],
"type": "string",
"description": "The parser BeautifulSoup uses for each page (its features argument). Naming a specific parser keeps results consistent across platforms. Only the parsers bundled with this Actor are available.",
"default": "html.parser"
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Specifies proxy servers that will be used by the scraper in order to hide its origin.",
"default": {
"useApifyProxy": true
}
}
}
},
"runsResponseSchema": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"actId": {
"type": "string"
},
"userId": {
"type": "string"
},
"startedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"finishedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"status": {
"type": "string",
"example": "READY"
},
"meta": {
"type": "object",
"properties": {
"origin": {
"type": "string",
"example": "API"
},
"userAgent": {
"type": "string"
}
}
},
"stats": {
"type": "object",
"properties": {
"inputBodyLen": {
"type": "integer",
"example": 2000
},
"rebootCount": {
"type": "integer",
"example": 0
},
"restartCount": {
"type": "integer",
"example": 0
},
"resurrectCount": {
"type": "integer",
"example": 0
},
"computeUnits": {
"type": "integer",
"example": 0
}
}
},
"options": {
"type": "object",
"properties": {
"build": {
"type": "string",
"example": "latest"
},
"timeoutSecs": {
"type": "integer",
"example": 300
},
"memoryMbytes": {
"type": "integer",
"example": 1024
},
"diskMbytes": {
"type": "integer",
"example": 2048
}
}
},
"buildId": {
"type": "string"
},
"defaultKeyValueStoreId": {
"type": "string"
},
"defaultDatasetId": {
"type": "string"
},
"defaultRequestQueueId": {
"type": "string"
},
"buildNumber": {
"type": "string",
"example": "1.0.0"
},
"containerUrl": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "integer",
"example": 1
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
},
"usageTotalUsd": {
"type": "number",
"example": 0.00005
},
"usageUsd": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "number",
"example": 0.00005
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
}
}
}
}
}
}
}
}